{"id":"W3132725505","doi":"10.48550/arxiv.2102.06966","title":"Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Graph; Classifier (UML); Linear classifier; Separable space; Mathematics; Convolution (computer science); Computer science; Pattern recognition (psychology); Artificial intelligence; Graphical model; Algorithm; Discrete mathematics; Artificial neural network","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004858671,0.0002234335,0.0002948722,0.0001084286,0.0001843157,0.0001017063,0.0005581535,0.0003154829,0.000005352675],"category_scores_gemma":[0.0001862488,0.0002678112,0.0001497323,0.0004040861,0.0001184101,0.0004037105,0.0004566819,0.0002682356,0.000001899854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001435119,"about_ca_system_score_gemma":0.0002187926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001064864,"about_ca_topic_score_gemma":0.00004751235,"domain_scores_codex":[0.9980866,0.0002524315,0.0003204396,0.001066206,0.00008061289,0.0001936624],"domain_scores_gemma":[0.9976769,0.0001146871,0.0004341395,0.001081073,0.0005911285,0.0001020625],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000355014,0.0009802515,0.05714813,0.002787895,0.0004390798,0.00001300487,0.001999518,0.1449159,0.01942246,0.757189,0.00161743,0.01313228],"study_design_scores_gemma":[0.0005017834,0.00004919487,0.01494132,0.00004453487,0.00007168224,8.469503e-7,0.00007813444,0.9787208,0.000314455,0.004174032,0.0008510062,0.0002521764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1603923,0.00007590214,0.8380566,0.0002207609,0.0004966229,0.000427326,0.0001348413,0.0001338472,0.00006178598],"genre_scores_gemma":[0.9888292,0.0002473093,0.007430868,0.00002720797,0.000079114,0.000006850406,0.003199036,0.00001059096,0.0001698098],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8338049,"threshold_uncertainty_score":0.9999774,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08802823376145545,"score_gpt":0.2319680894281704,"score_spread":0.143939855666715,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}